Cleaning control method and device for one-piece septic tank

By monitoring the real-time data of the array and basic design information analysis in the septic tank, a cleaning control solution is generated, which solves the problem of septic tank cleaning control errors in the prior art, and achieves more accurate and efficient septic tank cleaning.

CN118655782BActive Publication Date: 2024-11-15NANTONG GRIS PACKAGING TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411117088.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-15
Estimated Expiration
2044-08-15

AI Technical Summary

Technical Problem

The existing septic tank management device relies on a regular schedule for cleaning, ignoring the actual use of septic tanks and the accumulation rate of dirt, resulting in large errors in cleaning control, which may lead to premature or failure to clean in time, wasting resources or the environment. pollute.

Method used

By laying a monitoring array in the septic tank, real-time monitoring data and basic design information are extracted, cleaning control factors are determined based on real-time data analysis, whether cleaning is required, and development trend factors and directions are determined through situation analysis, cleaning control solutions are generated, and cleaning control solutions are optimized. Cleaning operation.

Benefits of technology

It improves the accuracy of septic tank cleaning control, reduces unnecessary cleaning times, avoids waste of resources and environmental pollution, and ensures timely cleaning of septic tanks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118655782B_ABST
    Figure CN118655782B_ABST
Patent Text Reader

Abstract

The present invention discloses a cleaning control method and device for an integrally formed septic tank, and relates to the technical field of data processing. The method comprises: extracting monitoring data of a monitoring array arranged in a target septic tank at the current moment, obtaining K real-time monitoring data of K monitoring points; collecting basic design information of the target septic tank; determining a real-time cleaning control factor; judging whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor, and if so, performing a situation analysis, determining K development trend factors and K development trend directions, combining the basic design information and the K real-time monitoring data to perform cleaning scheme configuration optimization, generate a target cleaning control scheme, and execute cleaning of the target septic tank. The present invention solves the technical problem in the prior art that the state analysis of the septic tank is insufficient, resulting in large errors in cleaning control, and achieves the technical effect of improving the reliability and accuracy of cleaning control.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a cleaning control method and device for an integrally formed septic tank. Background Art

[0002] Current septic tank management systems often rely on regular schedules for cleaning rather than real-time status data. This approach ignores the actual usage of the septic tank and the rate of dirt accumulation, which may result in some septic tanks being cleaned prematurely when they are not full, wasting resources, or some septic tanks being over capacity and not being treated in time, leading to overflows and environmental pollution.

[0003] The existing technology has a technical problem that the status analysis of the septic tank is not sufficient, resulting in large errors in cleaning control. Summary of the invention

[0004] The present application provides a cleaning control method and device for an integrally formed septic tank, which is used to solve the technical problem in the prior art that the state analysis of the septic tank is insufficient, resulting in large errors in cleaning control.

[0005] In view of the above problems, the present application provides a cleaning control method and device for an integrated septic tank.

[0006] In a first aspect of the present application, a cleaning control method for an integrated septic tank is provided, the method comprising:

[0007] Extract the monitoring data of the monitoring array deployed in the target septic tank at the current moment, and obtain K real-time monitoring data of K monitoring points, where K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1;

[0008] Collecting basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe;

[0009] Performing cleaning control analysis based on the K real-time monitoring data and the basic design information to determine a real-time cleaning control factor;

[0010] Determine whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, extract K associated monitoring data sets located in the preset associated window before the current moment, perform situation analysis on the K associated monitoring data sets, and determine K development trend factors and K development trend directions;

[0011] Performing cleaning scheme configuration optimization according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions to generate a target cleaning control scheme;

[0012] The target cleaning control scheme is sent to a cleaning control unit to execute cleaning of the target septic tank.

[0013] In a second aspect of the present application, a cleaning control device for an integrally formed septic tank is provided, the device comprising:

[0014] A real-time monitoring data acquisition module is used to extract the monitoring data of the monitoring array deployed in the target septic tank at the current moment, and obtain K real-time monitoring data of K monitoring points, where K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1;

[0015] A basic design information collection module is used to collect the basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe;

[0016] A real-time cleaning control factor determination module, used to perform cleaning control analysis based on the K real-time monitoring data and the basic design information to determine the real-time cleaning control factor;

[0017] A development trend direction determination module is used to determine whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor. If so, K associated monitoring data sets of a preset associated window before the current moment are extracted, and a situation analysis is performed on the K associated monitoring data sets to determine K development trend factors and K development trend directions;

[0018] A cleaning control scheme generation module, used to optimize the cleaning scheme configuration according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions, and generate a target cleaning control scheme;

[0019] The cleaning module is used to send the target cleaning control scheme to the cleaning control unit to execute the cleaning of the target septic tank.

[0020] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0021] The present application obtains K real-time monitoring data of K monitoring points by extracting the monitoring data of the monitoring array arranged in the target septic tank at the current moment, wherein K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1, and then collects the basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe, and then performs cleaning control analysis based on the K real-time monitoring data and the basic design information, determines the real-time cleaning control factor, and determines whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, extract the K associated monitoring data sets of the preset associated window before the current moment, perform situation analysis on the K associated monitoring data sets, determine K development trend factors and K development trend directions, and then perform cleaning scheme configuration optimization according to the basic design information and the K real-time monitoring data, the K development trend factors and the K development trend directions, generate a target cleaning control scheme, send the target cleaning control scheme to the cleaning control unit, and execute the cleaning of the target septic tank. The technical effect of fully analyzing the state of the target septic tank and improving the accuracy of cleaning control is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic flow chart of a cleaning control method for an integrated septic tank provided in an embodiment of the present application;

[0024] Figure 2 A schematic structural diagram of a cleaning control device for an integrally formed septic tank provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: real-time monitoring data acquisition module 11, basic design information collection module 12, real-time cleaning control factor determination module 13, development trend direction determination module 14, cleaning control scheme generation module 15, cleaning module 16. DETAILED DESCRIPTION

[0026] The present application provides a cleaning control method and device for an integrally formed septic tank, aiming to solve the technical problem in the prior art that the status analysis of the septic tank is insufficient, resulting in large errors in cleaning control.

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] like Figure 1 As shown, the present application provides a cleaning control method for an integrated septic tank, wherein the method comprises:

[0031] S100: extracting the monitoring data of the monitoring array arranged in the target septic tank at the current moment, and obtaining K real-time monitoring data of K monitoring points, wherein K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1;

[0032] In a possible embodiment, the target septic tank is a three-grid PE integrated septic tank, including a manure inlet pipe, a compartment tank, a connecting pipe, an outlet pipe and a cover plate. In order to determine the operating status of the target septic tank, K monitoring points are arranged in the target septic tank, and a monitoring sensor is arranged at each monitoring point. Optionally, the K monitoring sensors in the monitoring array include a temperature sensor, a humidity sensor, a water level monitor and a PH monitoring sensor.

[0033] By extracting data from the K monitoring sensors at the K monitoring points at the current moment, the state of the target septic tank at the current moment is obtained, and the K real-time monitoring data are obtained. The K real-time monitoring data include real-time temperature data, real-time humidity data, real-time water level, and real-time pH value. Obtaining the K real-time monitoring data provides reliable basic data for subsequent analysis of whether to clean the target septic tank and determination of specific cleaning control parameters when cleaning is required.

[0034] S200: Collecting basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe;

[0035] In a possible embodiment, due to different needs, the sizes and specifications of the septic tanks used are different. Therefore, in order to improve the accuracy of cleaning control, it is necessary to master the design of the target septic tank. The basic design information of the target septic tank is retrieved, wherein the basic design information is used to describe the specifications of the target septic tank, including the volume of the three compartment tanks, the diameter of the connecting pipe and the diameter of the outlet pipe.

[0036] The three compartment tanks are the main tank, the sedimentation tank, and the filtration tank. The main tank (main body tank) is the main part of the septic tank, which is used to collect and store sewage and solid waste entering the septic tank. The main tank is designed to ensure that sewage can be effectively settled, separate larger solid particles, and transport the liquid part downward for further treatment. The sedimentation tank is usually located after the main tank and is used to further separate and settle the solid matter at the bottom. This stage helps to reduce the amount of silt and solid waste at the bottom, making the liquid part clearer. The filtration tank is the last stage, and its main function is to further purify the liquid part through filter media (such as sand, gravel, etc.). This step can remove tiny suspended solids and organic matter in the water, making the treated liquid cleaner.

[0037] S300: performing cleaning control analysis based on the K real-time monitoring data and the basic design information to determine a real-time cleaning control factor;

[0038] In a possible embodiment, multiple sample real-time monitoring data, multiple sample basic design information, and multiple sample real-time cleaning control factors are obtained as basic construction data, and the basic construction data is used to supervise the training of the network framework constructed based on the feedforward neural network. During the training, the mapping relationship between the real-time monitoring data, the basic design information, and the real-time cleaning control factor is learned until the model output reaches convergence, and then a cleaning control analysis channel with training is obtained. The K real-time monitoring data and the basic design information are input into the cleaning control analysis channel for analysis to obtain the real-time cleaning control factor.

[0039] S400: Determine whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, extract K associated monitoring data sets in the preset associated window before the current moment, perform situation analysis on the K associated monitoring data sets, and determine K development trend factors and K development trend directions;

[0040] In one possible implementation, the preset cleaning control factor is a minimum cleaning control factor preset by a person skilled in the art when cleaning of the septic tank is required. When the real-time cleaning control factor is greater than or equal to the preset cleaning control factor, it indicates that the target septic tank needs to be cleaned at this time, and then K associated monitoring data sets of the preset associated window before the current moment are extracted, and the data development trends of the K monitoring points are analyzed according to the K associated monitoring data sets, so as to determine the K development trend factors and K development trend directions.

[0041] Optionally, the K development trend factors are the degree of increase or decrease of the monitoring data of the K monitoring points. The K development trend directions are the increase or decrease of the monitoring data of the K monitoring points within a preset correlation window. A situation analysis coordinate system is constructed with time as the horizontal coordinate and the associated monitoring data as the vertical coordinate.

[0042] The K associated monitoring data sets are respectively input into the situation analysis coordinate system to obtain K situation analysis curves. The gradients of the K situation analysis curves are calculated, and the calculation results are used as the K development trend factors. According to the positive and negative gradients in the calculation results, the K development trend directions are determined. If the gradient is positive, the development trend direction is increasing, and if the gradient is negative, the development trend direction is decreasing. By performing situation analysis, the data changes of the K monitoring points are mastered, providing a basis for subsequent reliable cleaning control.

[0043] Furthermore, step S400 in the embodiment of the present application further includes:

[0044] Determine whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor, and if not, perform dual-channel monitoring based on the real-time cleaning control factor to obtain a first monitoring frequency and a second monitoring frequency, wherein the first monitoring frequency is greater than or equal to the second monitoring frequency;

[0045] configuring a continuous monitoring channel based on the first monitoring frequency and the second monitoring frequency;

[0046] Using the continuous monitoring channel, the monitoring data of the K monitoring points within the preset continuous monitoring window after the current moment are analyzed to obtain a continuous monitoring cleaning control factor;

[0047] When the continuously monitored cleaning control factor is greater than or equal to the preset cleaning control factor, a situation analysis is triggered to obtain the K development trend factors and the K development trend directions.

[0048] Furthermore, step S400 in the embodiment of the present application further includes:

[0049] Construct monitoring frequency identification network layer;

[0050] The real-time cleaning control factor is identified by using the monitoring frequency identification network layer to obtain the first monitoring frequency and the second monitoring frequency.

[0051] Furthermore, step S400 in the embodiment of the present application further includes:

[0052] Acquire a plurality of sample monitoring data sets, a plurality of sample first extraction data sets, a plurality of sample second extraction data sets, a first monitoring frequency and the second monitoring frequency, and a plurality of sample continuous monitoring cleaning control factors as first training data;

[0053] Performing supervised training on the first monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample first extracted data sets, and the first monitoring frequency, and updating network parameters according to the training output results to obtain the first monitoring branch that has completed training;

[0054] Performing supervised training on the second monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample second extracted data sets, and the second monitoring frequency, and updating network parameters according to the training output results to obtain the trained second monitoring branch;

[0055] Extracting a plurality of sample first extracted data sets, a plurality of sample second extracted data sets and a plurality of sample continuous monitoring cleaning control factors from the first training data to perform supervised training on a network layer constructed based on a convolutional neural network, and when the model reaches convergence, obtaining a trained control factor identification layer;

[0056] The continuous monitoring channel is constructed based on the first monitoring branch, the second monitoring branch and the control factor identification layer.

[0057] In another possible implementation, when the real-time cleaning control factor is less than the preset cleaning control factor, it indicates that the target septic tank does not need to be cleaned at this time. The present application determines the operating state of the target septic tank according to the size of the real-time cleaning control factor, and then determines the corresponding first monitoring frequency and second monitoring frequency. Among them, the first monitoring frequency is greater than or equal to the second monitoring frequency. The first monitoring frequency is the first data amount extracted from the monitoring sensors deployed at the monitoring points per unit time. The second monitoring frequency is the second data amount extracted from the monitoring sensors deployed at the monitoring points per unit time.

[0058] In order to reliably analyze the data changes of K monitoring points within the preset continuous monitoring window, it is necessary to use the first monitoring branch and the second monitoring branch in the continuous monitoring channel to extract the monitoring data of the K monitoring points within the preset continuous monitoring window at different frequencies, so as to achieve the technical effect of improving data analysis efficiency while ensuring the reliability of processed data.

[0059] In one embodiment, the real-time cleaning control factor is identified by using a monitoring frequency identification network layer, thereby obtaining the first monitoring frequency and the second monitoring frequency. A plurality of sample real-time cleaning control factors and a plurality of sample first monitoring frequencies and a plurality of sample second monitoring frequencies are obtained as network layer construction data. The monitoring frequency identification network layer has two output layers, and the monitoring frequency identification network layer is supervised and trained using the network layer construction data, and the cross entropy loss algorithm is used to calculate the loss of the training process during training, and the parameters of the monitoring frequency identification network layer are optimized using the Adam optimizer according to the calculation results until a certain number of training iterations is reached or the loss converges.

[0060] A continuous monitoring channel is configured according to the first monitoring frequency and the second monitoring frequency obtained, wherein the continuous monitoring channel is used to perform intelligent continuous monitoring of the operating status of the target septic tank. The monitoring data of K monitoring points within the preset continuous monitoring window after the current moment are extracted to obtain K continuous monitoring data sets. The K continuous monitoring data sets are input into the continuous monitoring channel, and after data extraction from the first monitoring branch and the second monitoring branch, K first continuous monitoring extracted data sets and K second continuous monitoring extracted data sets are obtained. The control factor identification layer is used to identify the K first continuous monitoring extracted data sets and the K second continuous monitoring extracted data sets to obtain the continuous monitoring cleaning control factor. The continuous monitoring cleaning control factor reflects the operating status of the target septic tank when continuous monitoring is performed after the current moment.

[0061] When the continuously monitored cleaning control factor is greater than or equal to the preset cleaning control factor, a situation analysis is triggered, indicating that the target septic tank needs to conduct development situation analysis of K monitoring points at this time, so as to obtain the K development trend factors and the K development trend directions.

[0062] Optionally, a plurality of sample monitoring data sets, a plurality of sample first extraction data sets, a plurality of sample second extraction data sets, a first monitoring frequency and a second monitoring frequency, and a plurality of sample continuous monitoring cleaning control factors are obtained as first training data. The first training data is used to construct the continuous monitoring channel.

[0063] Optionally, multiple sample monitoring data sets, multiple sample first extraction data sets and the first monitoring frequency in the first training data are used as first monitoring branch training data, and the first monitoring branch training data is used to perform supervised training on the first monitoring branch constructed based on the convolutional neural network. During the training, the mapping relationship between the monitoring data set, the first monitoring frequency and the first extraction data set is learned, and the network parameters of the first monitoring branch are updated according to the training output results, so as to obtain the first monitoring branch that has completed training.

[0064] Optionally, based on the same construction principle as the first monitoring branch, the second monitoring branch is supervised trained using multiple sample monitoring data sets, multiple sample second extracted data sets and the second monitoring frequency in the first training data, and the mapping relationship between the monitoring data set, the second monitoring frequency and the second extracted data set is learned during training, and the network parameters of the second monitoring branch are updated according to the training output results to obtain the trained second monitoring branch.

[0065] Extract multiple sample first extraction data sets, multiple sample second extraction data sets and multiple sample continuous monitoring cleaning control factors from the first training data again to supervise the network layer constructed based on the convolutional neural network, and learn the mapping relationship between the first extraction data set and the second extraction data set and the continuous monitoring cleaning control factor during the training. When the model reaches convergence, the trained control factor identification layer is obtained. The first monitoring branch and the second monitoring branch are connected in parallel, and the outputs of the first monitoring branch and the second monitoring branch are connected to the input of the control factor identification layer to generate the continuous monitoring channel.

[0066] S500: performing cleaning scheme configuration optimization according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions to generate a target cleaning control scheme;

[0067] S600: Send the target cleaning control scheme to the cleaning control unit to execute cleaning of the target septic tank.

[0068] Further, the cleaning scheme configuration is optimized according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions to generate a target cleaning control scheme. Step S500 of the embodiment of the present application also includes:

[0069] Performing cleaning scheme configuration based on the basic design information and the K real-time monitoring data to obtain an initial cleaning control scheme;

[0070] According to the K development trend factors and the K development trend directions, a number of real-time monitoring data are randomly selected from the K real-time monitoring data for fine-tuning multiple times to obtain multiple fine-tuning monitoring data sets, wherein each fine-tuning monitoring data set includes K fine-tuning real-time monitoring data;

[0071] The initial cleaning control scheme is optimized based on the multiple fine-tuning monitoring data sets to obtain a target cleaning control scheme.

[0072] Furthermore, step S500 of the embodiment of the present application further includes:

[0073] Perform cleaning scheme configuration according to the basic design information and the plurality of fine-tuning monitoring data sets to obtain a plurality of fine-tuning cleaning control schemes;

[0074] Based on the multiple fine-tuning cleaning control parameter sets of the multiple fine-tuning cleaning control schemes, adjusting the initial cleaning control parameter set in the initial cleaning control scheme to obtain an adjusted cleaning control parameter set;

[0075] The target cleaning control scheme is generated based on the set of adjusted cleaning control parameters.

[0076] Furthermore, the initial cleaning control parameter set includes a water pump start time, a water pump stop time and a suction frequency.

[0077] In a possible embodiment, the real-time status of the K monitoring points of the target septic tank can be obtained based on the K real-time monitoring data, the data development status of the K monitoring points can be obtained according to the K development trend factors and K development trend directions, and the cleaning scheme configuration can be optimized in combination with the structure of the target septic tank reflected by the basic design information, and the target cleaning control scheme is obtained according to the optimization result. Among them, the target cleaning control scheme is a scheme for describing the control parameters used when cleaning the target septic tank. The target cleaning control scheme includes the target water pump start time, the target water pump stop time and the target water pump suction frequency.

[0078] Optionally, the target cleaning control scheme is sent to a cleaning control unit, and the cleaning control unit is used to control a water pump to clean the target septic tank, thereby achieving the technical effect of cleaning in combination with the actual conditions of the septic tank and improving the accuracy and reliability of cleaning control.

[0079] In an embodiment of the present application, multiple sample basic design information and multiple sample real-time monitoring data sets (each sample real-time monitoring data set includes K sample real-time monitoring data), as well as corresponding multiple sample cleaning control schemes, are obtained. A cleaning control scheme mapping table is constructed based on a two-to-one mapping relationship between the basic design information and the sample real-time monitoring data and the sample cleaning control scheme. The basic design information and K real-time monitoring data are input into the cleaning control scheme mapping table and retrieved using the interpolation method to obtain the initial cleaning control scheme. The initial cleaning control scheme includes an initial cleaning control parameter set, and the initial cleaning control parameter set includes a water pump start time, a water pump stop time, and a suction frequency.

[0080] A plurality of real-time monitoring data are randomly extracted from the K real-time monitoring data for multiple times, and the randomly extracted real-time monitoring data are fine-tuned according to the size of the K development trend factors and the increase or decrease direction of the K development trend directions, so as to obtain the plurality of fine-tuned monitoring data sets. Each fine-tuned monitoring data set includes K fine-tuned real-time monitoring data. That is, a plurality of real-time monitoring data are randomly extracted from the K real-time monitoring data for fine-tuning each time, so as to expand the analysis sample.

[0081] Due to the influence of different monitoring accuracy of sensors and changes in environmental factors, it is necessary to consider the fluctuation of K real-time monitoring data to ensure the accuracy of analysis. By obtaining multiple fine-tuning monitoring data sets, the fluctuation of K real-time monitoring data can be expanded to improve the reliability of subsequent cleaning control.

[0082] In one embodiment, multiple fine-tuning monitoring data sets and the basic design information are respectively input into the cleaning control scheme mapping table for retrieval, thereby obtaining the multiple fine-tuning cleaning control schemes. Multiple fine-tuning cleaning control parameter sets in the multiple fine-tuning cleaning control schemes are extracted, and the same fine-tuning cleaning control parameter in the multiple fine-tuning cleaning control parameter sets is extracted to obtain Q clusters of clustered fine-tuning cleaning control parameter clusters. Q is the number of parameters in the fine-tuning cleaning control scheme, which is an integer greater than or equal to 1. Each cluster of fine-tuning cleaning control parameter clusters includes all values ​​of a type of fine-tuning cleaning control parameter in the multiple fine-tuning cleaning control parameter sets. The mean of the Q clustered fine-tuning cleaning control parameter clusters is calculated respectively to obtain the means of the Q fine-tuning cleaning control parameters.

[0083] The Q fine-tuning cleaning control parameter means and the corresponding initial cleaning control parameter means in the initial cleaning control parameter set are calculated respectively to obtain Q adjustment cleaning control parameters. The Q adjustment cleaning control parameters are summarized to obtain the adjustment cleaning control parameter set. Furthermore, the adjustment cleaning control parameter set is used as the target cleaning control scheme.

[0084] In summary, the embodiments of the present application have at least the following technical effects:

[0085] This application achieves the goal of mastering the operating status of the target septic tank by extracting the monitoring data of the monitoring array deployed in the target septic tank at the current moment, obtaining K real-time monitoring data of K monitoring points, and then collecting the basic design information of the target septic tank, and then performing cleaning control analysis based on the K real-time monitoring data and basic design information, determining the real-time cleaning control factor, and judging whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, extracting K associated monitoring data sets of the preset associated window before the current moment, performing situation analysis on the K associated monitoring data sets, determining K development trend factors and K development trend directions, and achieving the goal of determining whether the target septic tank needs to be cleaned and controlled, and then combining the basic design information and K real-time monitoring data to optimize the cleaning scheme configuration, generate a target cleaning control scheme, send the target cleaning control scheme to the cleaning control unit, and execute the cleaning of the target septic tank. The technical effect of fully analyzing the status of the target septic tank, optimizing the cleaning scheme, reducing unnecessary cleaning times, and improving the accuracy of cleaning control is achieved.

[0086] Embodiment 2

[0087] Based on the same inventive concept as the cleaning control method for the integrated septic tank in the aforementioned embodiment, Figure 2 As shown, the present application provides a cleaning control device for an integrally formed septic tank, and the device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0088] The real-time monitoring data acquisition module 11 is used to extract the monitoring data of the monitoring array arranged in the target septic tank at the current moment, and obtain K real-time monitoring data of K monitoring points, wherein K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1;

[0089] A basic design information collection module 12 is used to collect the basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe;

[0090] A real-time cleaning control factor determination module 13, configured to perform cleaning control analysis based on the K real-time monitoring data and the basic design information to determine a real-time cleaning control factor;

[0091] The development trend direction determination module 14 is used to determine whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, K associated monitoring data sets located in the preset associated window before the current moment are extracted, and the K associated monitoring data sets are subjected to situation analysis to determine K development trend factors and K development trend directions;

[0092] A cleaning control scheme generating module 15 is used to optimize the cleaning scheme configuration according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions, and generate a target cleaning control scheme;

[0093] The cleaning module 16 is used to send the target cleaning control scheme to the cleaning control unit to execute the cleaning of the target septic tank.

[0094] Furthermore, the cleaning control scheme generating module 15 is used to perform the following steps:

[0095] Performing cleaning scheme configuration based on the basic design information and the K real-time monitoring data to obtain an initial cleaning control scheme;

[0096] According to the K development trend factors and the K development trend directions, a number of real-time monitoring data are randomly selected from the K real-time monitoring data for fine-tuning multiple times to obtain multiple fine-tuning monitoring data sets, wherein each fine-tuning monitoring data set includes K fine-tuning real-time monitoring data;

[0097] The initial cleaning control scheme is optimized based on the multiple fine-tuning monitoring data sets to obtain a target cleaning control scheme.

[0098] Furthermore, the cleaning control scheme generating module 15 is used to perform the following steps:

[0099] Perform cleaning scheme configuration according to the basic design information and the plurality of fine-tuning monitoring data sets to obtain a plurality of fine-tuning cleaning control schemes;

[0100] Based on the multiple fine-tuning cleaning control parameter sets of the multiple fine-tuning cleaning control schemes, adjusting the initial cleaning control parameter set in the initial cleaning control scheme to obtain an adjusted cleaning control parameter set;

[0101] The target cleaning control scheme is generated based on the set of adjusted cleaning control parameters.

[0102] Furthermore, the initial cleaning control parameter set includes a water pump start time, a water pump stop time and a suction frequency.

[0103] Furthermore, the development trend direction determination module 14 is used to perform the following steps:

[0104] Determine whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor, and if not, perform dual-channel monitoring based on the real-time cleaning control factor to obtain a first monitoring frequency and a second monitoring frequency, wherein the first monitoring frequency is greater than or equal to the second monitoring frequency;

[0105] configuring a continuous monitoring channel based on the first monitoring frequency and the second monitoring frequency;

[0106] Using the continuous monitoring channel, the monitoring data of the K monitoring points within the preset continuous monitoring window after the current moment are analyzed to obtain a continuous monitoring cleaning control factor;

[0107] When the continuously monitored cleaning control factor is greater than or equal to the preset cleaning control factor, a situation analysis is triggered to obtain the K development trend factors and the K development trend directions.

[0108] Furthermore, the development trend direction determination module 14 is used to perform the following steps:

[0109] Construct monitoring frequency identification network layer;

[0110] The real-time cleaning control factor is identified by using the monitoring frequency identification network layer to obtain the first monitoring frequency and the second monitoring frequency.

[0111] Furthermore, the development trend direction determination module 14 is used to perform the following steps:

[0112] Acquire a plurality of sample monitoring data sets, a plurality of sample first extraction data sets, a plurality of sample second extraction data sets, a first monitoring frequency and the second monitoring frequency, and a plurality of sample continuous monitoring cleaning control factors as first training data;

[0113] Performing supervised training on the first monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample first extracted data sets, and the first monitoring frequency, and updating network parameters according to the training output results to obtain the first monitoring branch that has completed training;

[0114] Performing supervised training on the second monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample second extracted data sets, and the second monitoring frequency, and updating network parameters according to the training output results to obtain the trained second monitoring branch;

[0115] Extracting a plurality of sample first extracted data sets, a plurality of sample second extracted data sets and a plurality of sample continuous monitoring cleaning control factors from the first training data to perform supervised training on a network layer constructed based on a convolutional neural network, and when the model reaches convergence, obtaining a trained control factor identification layer;

[0116] The continuous monitoring channel is constructed based on the first monitoring branch, the second monitoring branch and the control factor identification layer.

[0117] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0119] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A cleaning control method for an integrated septic tank, characterized in that: The method comprises: Extract the monitoring data of the monitoring array deployed in the target septic tank at the current moment, and obtain K real-time monitoring data of K monitoring points, where K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1; Collecting basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe; Performing cleaning control analysis based on the K real-time monitoring data and the basic design information to determine a real-time cleaning control factor; Determine whether the real-time cleaning control factor is greater than or equal to the preset cleaning control factor. If so, extract K associated monitoring data sets located in the preset associated window before the current moment, perform situation analysis on the K associated monitoring data sets, and determine K development trend factors and K development trend directions; Performing cleaning scheme configuration optimization according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions to generate a target cleaning control scheme; Sending the target cleaning control scheme to a cleaning control unit to perform cleaning of the target septic tank; Determine whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor, and if not, perform dual-channel monitoring based on the real-time cleaning control factor to obtain a first monitoring frequency and a second monitoring frequency, wherein the first monitoring frequency is greater than or equal to the second monitoring frequency; configuring a continuous monitoring channel based on the first monitoring frequency and the second monitoring frequency; Using the continuous monitoring channel, the monitoring data of the K monitoring points within the preset continuous monitoring window after the current moment are analyzed to obtain a continuous monitoring cleaning control factor; When the continuously monitored cleaning control factor is greater than or equal to the preset cleaning control factor, a situation analysis is triggered to obtain the K development trend factors and the K development trend directions; Construct monitoring frequency identification network layer; Using the monitoring frequency identification network layer to identify the real-time cleaning control factor, and obtaining the first monitoring frequency and the second monitoring frequency; Acquire a plurality of sample monitoring data sets, a plurality of sample first extraction data sets, a plurality of sample second extraction data sets, a first monitoring frequency and the second monitoring frequency, and a plurality of sample continuous monitoring cleaning control factors as first training data; Performing supervised training on the first monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample first extracted data sets, and the first monitoring frequency, and updating network parameters according to the training output results to obtain the first monitoring branch that has completed training; Performing supervised training on the second monitoring branch using multiple sample monitoring data sets in the first training data, multiple sample second extracted data sets, and the second monitoring frequency, and updating network parameters according to the training output results to obtain the trained second monitoring branch; Extracting a plurality of sample first extracted data sets, a plurality of sample second extracted data sets and a plurality of sample continuous monitoring cleaning control factors from the first training data to perform supervised training on a network layer constructed based on a convolutional neural network, and when the model reaches convergence, obtaining a trained control factor identification layer; The continuous monitoring channel is constructed based on the first monitoring branch, the second monitoring branch and the control factor identification layer.

2. The cleaning control method for an integrated septic tank according to claim 1, characterized in that: According to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions, a cleaning scheme configuration optimization is performed to generate a target cleaning control scheme, including: Performing cleaning scheme configuration based on the basic design information and the K real-time monitoring data to obtain an initial cleaning control scheme; According to the K development trend factors and the K development trend directions, a number of real-time monitoring data are randomly selected from the K real-time monitoring data for fine-tuning multiple times to obtain multiple fine-tuning monitoring data sets, wherein each fine-tuning monitoring data set includes K fine-tuning real-time monitoring data; The initial cleaning control scheme is optimized based on the multiple fine-tuning monitoring data sets to obtain a target cleaning control scheme.

3. The cleaning control method for an integrated septic tank according to claim 2, characterized in that: include: Perform cleaning scheme configuration according to the basic design information and the plurality of fine-tuning monitoring data sets to obtain a plurality of fine-tuning cleaning control schemes; Based on the multiple fine-tuning cleaning control parameter sets of the multiple fine-tuning cleaning control schemes, adjusting the initial cleaning control parameter set in the initial cleaning control scheme to obtain an adjusted cleaning control parameter set; The target cleaning control scheme is generated based on the set of adjusted cleaning control parameters.

4. The cleaning control method for an integrated septic tank according to claim 3, characterized in that: The initial cleaning control parameter set includes a water pump start time, a water pump stop time and a suction frequency.

5. A cleaning control device for an integrated septic tank, characterized in that: The device is used to implement the cleaning control method for an integrally formed septic tank according to any one of claims 1 to 4, and the device comprises: A real-time monitoring data acquisition module is used to extract the monitoring data of the monitoring array deployed in the target septic tank at the current moment, and obtain K real-time monitoring data of K monitoring points, where K is the number of monitoring sensors in the monitoring array, and K is an integer greater than or equal to 1; A basic design information collection module, used to collect the basic design information of the target septic tank, wherein the basic design information includes the volume of three compartment tanks, the diameter of the connecting pipe, and the diameter of the outlet pipe; A real-time cleaning control factor determination module, used to perform cleaning control analysis based on the K real-time monitoring data and the basic design information to determine the real-time cleaning control factor; A development trend direction determination module is used to determine whether the real-time cleaning control factor is greater than or equal to a preset cleaning control factor. If so, K associated monitoring data sets of a preset associated window before the current moment are extracted, and a situation analysis is performed on the K associated monitoring data sets to determine K development trend factors and K development trend directions; A cleaning control scheme generation module, used to optimize the cleaning scheme configuration according to the basic design information and K real-time monitoring data, K development trend factors and K development trend directions, and generate a target cleaning control scheme; The cleaning module is used to send the target cleaning control scheme to the cleaning control unit to execute the cleaning of the target septic tank.